predict_image() requires that the image is RGB format, but VideoCapture.read() returns BGR image,
so we need to convert the frame to RGB format.

* change coco dataset for npu tipc

* update link

* fix npu tipc script

* fix typo

* fix conflict

* add npu inference support

* fix typo

* add ppyoloe_sod_qat

* ppyoloe sod qat

* add ppyoloe_sod qat demo

* fix ppyoloe sod qat yml

* add ppyoloe-sod ppyoloe_tiny qat

* add ppyoloe_sod_qat readme

* metro con reverse

tinypose3d fix

readme modelzoo

* fix tinypose3d

* new adapted

* test ok

* keypoint petr (#7774)

* petr train ok

train ok

refix augsize

affine size fix

update msdeformable

fix flip/affine

fix clip

add resize area

add distortion

debug mode

fix pos_inds

update edge joints

update word mistake

* delete extra codes;adapt transformer modify;update code format

* reverse old transformer modify

* integrate datasets

* add config and architecture for human36m (#7802)

* add config and architecture for human36m

* modify TinyPose3DHRNet to support human3.6M dataset

* delete useless class

---------
Co-authored-by: XYZ <1290573099@qq.com>

* fix run_benchmark for small model accurate speed

* fix run_benchmark for other det models

* ppvehicle add customized docs, test=document_fix

* fix pipeline readme.md test=document_fix

* fix pipeline readme.md link test=document_fix

* add licensed to lane_to_mask.py

* ppvehicle_violation.md add args list test=document_fix

* pose3d docs

* traindata download

* fix smalldet docs, test=document_fix

* fix smalldet configs and readme, test=document_fix

* update pipeline docs; vehicle illegal;rtsp;jetson

* update docs

* bold text